NBSE identifies the Nishimori temperature where the Bethe Hessian singularizes to embed features via degree-corrected diffusion and selects one representative per redundant group, preserving accuracy at 30% retention on EfficientNet-B4.
The use of multiple measurements in taxonomic prob- lems
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Diffusion-Guided Feature Selection via Nishimori Temperature: Noise-Based Spectral Embedding
NBSE identifies the Nishimori temperature where the Bethe Hessian singularizes to embed features via degree-corrected diffusion and selects one representative per redundant group, preserving accuracy at 30% retention on EfficientNet-B4.